verify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires the agent to run arbitrary commands and "state the result, cite command, exit code, and key output" (and even shows a CLI with free-text content), which forces verbatim inclusion of command strings and outputs — risking exfiltration if those contain API keys, tokens, or passwords.